《Python机器学习建模与部署:从Keras到Kubernetes》资源链接清单

为方便读者查找,本文汇总了《Python机器学习建模与部署:从Keras到Kubernetes》一书中用到的部分网络资源链接。链接内容可能随时间变化,请读者知悉。

前言

需要的工具

  • Python网站(https://www.python.org/)
  • Jupyter官网(http://jupyter.org)
  • Pandas网站(https://pandas.pydata.org/)
  • Scikit-Learn网站(https://scikit-learn.org/)
  • TensorFlow网站(https://www.tensorflow.org)
  • 谷歌Colaboratory网站(https://colab.research.google.com)
  • Toolbox网站(https://toolbox.google.com/datasetsearch)

第3章 处理非结构化数据

3.2 理解图像

  • Yann Lecun、Corinna Cortes和Christopher J.C. Burges合著的文章“The Minist Database of Handwritten Digits”(http://yann.lecun.com/exdb/mnist)
  • OpenCV网站(https://docs.opencv.org/4.0.0/d6/d00/tutorial _ py _ root.html)
  • Wikipedia网站的《蒙娜丽莎》的图像(https://en.wikipedia.org/wiki/Mona _ Lisa)
  • GitHub 网站OpenCV 页面(https://github.com/opencv/opencv/tree/master/data/haarcascades)
  • 在OpenCV网站搜索OpenCV-Python Tutorials查看一些方法的详细信息(https://docs.opencv.org/4.0.0/d6/d00/tutorial _ py _ root.html)

3.4 处理文本数据

  • NLTK 3.5 documentation网站(https://www.nltk.org)

3.4.2 词嵌入

  • Gensim网站(https://radimrehurek.com/gensim/index.html)
  • 在论文“Efficient Estimation of Word Representations in VectorSpace”(https://arxiv.org/pdf/1301.3781.pdf)

第6章 前沿深度学习项目

6.1 神经风格迁移

  • GitHub 网站(搜索Keras-team/Keras)上查看代码(https://github.com/keras-team/keras/blob/master/examples/neural_style_transfer.py)
  • 媒体报道“Neural Style Transfer: Creating Art with Deep Learning Using tf.keras and Eager Execution”(https://medium.com/tensorflow/neural-style-transfer-creatingart-with-deep-learning-using-tf-keras-and-eager-execution-7d541ac31398)
  • 谷歌Colab Notebook(https://colab.research.google.com/drive/1_tHUYgO_fIBU1JXdn_mXWCDD6n-jLyNSu)

6.3 利用自编码器进行信用卡欺诈检测

  • 布鲁塞尔自由大学(ULB)机器学习小组(http://mlg.ulb.ac.be)

第7章 现代软件世界中的人工智能

7.6 Kubernetes:基础架构问题的CaaS解决方案

  • DockerHub(https://hub.docker.com)

第10章 机器学习平台

10.1 机器学习平台关注点

  • H2O.ai 网站上安装H2O的步骤(http://h2o-release.s3.amazonaws.com/h2o/rel-xu/1/index.html)

附录A

第1章 大数据和人工智能

  • GE网站其关于工业物联网前景的白皮书(https://www.ge.com/docs/chapters/Industrial _ Internet.pdf)
  • 文章“What isIndustry 4.0?”(https://www.forbes.com/sites/bernardmarr/2018/09/02/what-is-industry-4-0-heres-a-super-easy-explanation-for-anyone/#2c0bb9af9788)
  • 文章“Inside Amazon’s Artificial Intelligence Flywheel—How Deep Learning Came to Power Alexa, Amazon Web Services, and Nearly Every Other Division of the Company”(https://www.wired.com/story/amazon-artificial-intelligence-flywheel)
  • CHRISTIE’S 网站的文章“Is Artificial Intelligence Set to Become Art’s Next Medium?”(https://www.christies.com/features/A-collaboration-betweentwo-artists-one-human-one-a-machine-9332-1.aspx)
  • THEVERGE 网站的文章“All of These Faces are Fake Celebrities Spawned by AI”(https://www.theverge.com/2017/10/30/16569402/ai-generate-fake-faces-celebs-nvidia-gan)
  • 谷歌的Google AI网站(https://ai.google/)
  • Facebook的ONNX网站(https://onnx.ai)
  • NVIDIA的Deep Learning AI网站(https://www.nvidia.com/en-gb/deep-learning-ai/)
  • 英特尔的人工智能网站(https://software.intel.com/en-us/ai-academy)
  • IBM Watson网站(https://www.ibm.com/watson/)
  • SalesForce网站(https://www.salesforce.com/products/einstein/overview/)
  • H2O.ai网站(https://www.h2o.ai/)

第2章 机器学习

  • 吴恩达博士的视频课程(https://www.coursera.org/learn/machine-learning、 https://www.deeplearning.ai/和https://www.youtube.com/user/StanfordUniversity)
  • 谷歌提供的机器学习方面的在线免费速成课程(https://developers.google.com/machine-learning/crash-course/ml-intro)
  • ocdevel网站(http://ocdevel.com/mlg)
  • Talking Machines网站(https://www.thetalkingmachines.com/)
  • SoundCloud网站(https://soundcloud.com/datahack-radio)
  • O’Reilly Data Show Podcast(https://soundcloud.com/datahack-radio)
  • Analytics Vidhya网站的优秀教程(https://www.analyticsvidhya.com/blog/2017/09/common-machine-learning-algorithms/、https://www.analyticsvidhya.com/blog/2016/01/complete-tutorial-learn-data-science-python-scratch-2/、https://www.analyticsvidhya.com/blog/2018/03/comprehensive-collection-deep-learning-datasets/)
  • Kaggle网站(https://www.kaggle.com/)

第3章 处理非结构化数据

  • OpenCV教程网站(https://docs.opencv.org/3.0-beta/doc/py _ tutorials/py _ tutorials.html)
  • Adrian开设的计算机视觉速成课程(https://www.pyimagesearch.com/)
  • Scikit-Learn提供的教程(https://scikit-learn.org/stable/tutorial/index.html)
  • DZone网站上的文章“NLP Tutorial Using Python NLTK(Simple Examples)”(https://dzone.com/articles/nlp-tutorial-using-python-nltk-simpleexamples)

第4章 使用Keras 进行深度学习

  • TensorFlow网站的代码测试(https://www.tensorflow.org/tutorials/)
  • GitHub网站上一些有用的Keras资源(https://github.com/fchollet/keras-resources)

第5章 高级深度学习

  • KDnuggets网站上使用Keras的深度学习文章(https://www.kdnuggets.com/2017/10/seven-stepsdeep-learning-keras.html)

第6章 前沿深度学习项目

  • 技术论文“A Neural Algorithm of Artistic Style”(https://arxiv.org/abs/1508.06576)
  • RaymondYuan提供的带有样本代码的神经风格迁移帖子(https://medium.com/tensorflow/neural-style-transfer-creating-artwith-deep-learning-using-tf-keras-and-eager-execution-7d541ac31398)
  • 技术论文“Generative Adversarial Networks”(https://arxiv.org/abs/1406.2661)
  • Analytics Vidhya网站中含有的关于生成对抗网络的文章(https://www.analyticsvidhya.com/blog/2017/06/introductory-generative-adversarial-networks-gans/)
  • 文章“Fraud Detection Using Autoencoders in Keras with a TensorFlow Backend”(https://www.datascience.com/blog/fraud-detection-with-tensorflow)

第7章 现代软件世界中的人工智能

  • Kubernetes网站提供的关于设置集群的优秀互动教程(https://kubernetes.io/docs/tutorials/kubernetes-basics/)
  • Katacoda网站提供的优秀互动教程(https://www.katacoda.com/courses/kubernetes)

第8章 将人工智能模型部署为微服务

  • Martin Fowler和James Lewis撰写的有关微服务架构的优秀概述教程(https://martinfowler.com/articles/microservices.html)
  • 作者的GitHub仓库(https://github.com/dattarajrao/keras2kubernetes)

第9章 机器学习开发生命周期

  • Mesosphere撰写的优秀白皮书Design & Build an End-to-End Data Science Platform(https://mesosphere.com/resources/building-data-science-platform/)
  • 谷歌云平台团队的在YouTube网站上的视频“The 7 Steps of Machine Learning”(https://www.youtube.com/watch?v=nKW8Ndu7Mjw)
  • 博客文章“Data Scientists and Deploying Machine Learning into Production— Not a Great Match”(https://blog.algorithmia.com/data-scientists-and-deploying-machinelearning-into-production-not-a-great-match/)

第10章 机器学习平台

  • 博客“Let’s Flow within Kubeflow”(https://ai.intel.com/lets-flow-within-kubeflow/)
  • 文章“Serving ML Quickly with TensorFlow Serving and Docker”(https://medium.com/tensorflow/serving-ml-quickly-with-tensorflowserving-and-docker-7df7094aa008)
  • Katacoda关于使用Kubeflow和Kubernetes部署机器学习工作负载的交互式教程(https://www.katacoda.com/kubeflow/scenarios/deploying-kubeflow)